Towards a digital twin framework in additive manufacturing: Machine learning and bayesian optimization for time series process optimization

Damage identification of offshore jacket platforms in a digital twin framework considering optimal sensor placement

4SQR-Code: A 4-state QR code generation model for increasing data storing capacity in the Digital Twin framework

Microtexture in additively manufactured Ti-6Al-4V fabricated using directed energy deposition

The article focuses on the project to develop a supply chain management information system using a digital twin for the maritime transport chain. Digital twins reflect real objects and processes in a virtual environment, which enables analysis, modelling and optimisation of supply chain operations. The author describes the main stages of the project, including requirements definition, system architecture development, implementation and testing. Particular attention is paid to the benefits of using digital twins in supply chain management, such as increased efficiency, reduced risk and improved forecasting. The results of the study show the potential of digital twins to optimise supply chain management and increase the competitiveness of companies. The article presents an approach to building a new model of interaction and systematic optimisation of business processes based on digital technologies at all stages of supply chain formation, which ensures the creation of a digital twin for the maritime transport chain. In order to improve supply chains, a digital twin has been proposed, which opens up great prospects for the management of logistics processes and the exchange of information between supply chain participants. This paper presents a framework for an integral Digital Supply Chain Twin (DSCT) capable of covering the entire transport chain. The proposed information system based on the use of the DSCT provides a number of improvements throughout the supply chain, as well as the ability to model and evaluate different scenarios for the supply chain. This creates opportunities to reduce the cost of organising and coordinating transport, improve the quality of transport and logistics services and make them more reliable by identifying potential problems at an early stage. The article analyses the main information technologies that facilitate the use of DSCT as a useful and reliable tool.

BackgroundAlzheimer’s disease (AD) is a complex and poorly understood neurodegenerative disorder with a lack of effective treatments. Novel approaches for identifying FDA‐approved drugs with potential for AD treatment hold promise to address this challenge. One promising approach involves leveraging digital twins (DTs), which are virtual representations of physical entities by integrating advanced technologies such as artificial intelligence (AI), statistical modeling, network medicine, and multi‐omics analysis. DTs enable real‐time characterization of disease heterogeneities through continuous feedback and dynamic model updates, facilitating the identification of therapeutic targets.MethodIn this study, we developed a single‐cell Digital Twin (scDT) framework to model AD progression by integrating single‐nuclei RNA‐seq (snRNA‐seq; 1,197,032 nuclei) and ATAC‐seq (snATAC‐seq; 740,875 nuclei) data from the middle temporal gyrus (MTG) of 84 donors across four stages (non‐AD, low, intermediate, and high) of AD neuropathological changes (ADNC) from the SEA‐AD cohort. This framework enabled prioritization of AD‐associated genes and identification of potential candidate drugs through a combination of gene set enrichment analysis (GSEA) and network proximity analysis.ResultWe annotated six major cell types for snRNA‐seq and snATAC‐seq and observed distinct gene expression dynamics among these six major cell types during the early stages of ADNC, with these differences becoming more pronounced in high ADNC. By constructing cell type‐specific transcription factor (TF)‐target gene regulatory networks through leveraging peak‐to‐gene linkages and motif enrichment analyses, we identified cell type‐specific candidate cis‐regulatory DNA elements (cCREs). Integration of genome‐wide association study (GWAS) loci with cell type‐specific cCREs revealed 141 ADNC‐associated genes, including 36 genes targeted by FDA‐approved or clinically investigational therapies (e.g., ACE, ABCA1, and CRHR1). Furthermore, GSEA and network proximity analyses highlighted 13 repurposable drugs (e.g., galantamine, mecamylamine, dextromethorphan, tubocurarine, gabapentin, ebselen, resveratrol, imatinib, dipyridamole, deferoxamine, gemfibrozil, lansoprazole, and probucol) associated with these ADNC‐linked genes.ConclusionIn summary, we demonstrated a single‐cell digital twin framework for cell type‐specific target identification and drug repurposing in AD and other AD‐related dementia if broadly applied.

Unmanned aerial vehicle base stations (UAV-BSs) have shown significant promise in enabling rapid communication recovery in disaster scenarios. However, existing approaches are often task-specific or heuristic-based, lacking the adaptability to handle UAV-BS deployment in uncertain, dynamic disaster scenarios. To address these issues, we propose an artificial general intelligence (AGI) inspired digital twin (DT) framework for UAV-BS deployment, aligning the design of DT with AGI’s closed-loop architecture consisting of perception, modeling, and action planning. Specifically, the proposed DT framework includes a predictor and an optimizer. The predictor, implemented by a graph neural network (GNN) and multilayer perceptron (MLP), performs perception and modeling of real UAV-BS network states and predicts service satisfaction. The optimizer, developed based on hierarchical reinforcement learning (HRL), performs action planning by adaptively determining the number and trajectories of UAV-BSs, subject to multiple network performance and operational constraints. A self-evolving loop is formed through online learning, which continuously updates the DT using feedback from the real UAV-BS network. Extensive simulation experiments are conducted to validate the effectiveness of the proposed DT, with the predictor achieving 98.49% for average accuracy on service satisfaction and the optimizer reducing training time by 63.73% compared to multi-level deep Q-learning. Additionally, optimized UAV-BS deployment decisions can be generated within 0.086 seconds when the disaster environment condition changes.

Generation IV (Gen-IV) nuclear power plants are envisioned to replace the current reactor fleet, bringing improvements in performance, safety, reliability, and sustainability. However, large cost investments currently inhibit the deployment of these advanced reactor concepts. Digital twins bridge real-world systems with digital tools to reduce costs, enhance decision-making, and boost operational efficiency. In this work, a digital twin framework is designed to operate the Gen-IV Fluoride-salt-cooled High-temperature Reactor (FHR), utilizing data-enhanced methods to optimize operational and maintenance policies while adhering to system constraints. The closed-loop framework integrates surrogate modeling, reinforcement learning, and Bayesian inference to streamline end-to-end communication for online regulation and self-adjustment. Reinforcement learning is used to consider component health and degradation to drive the target power generations, with constraints enforced through a Reference Governor control algorithm that ensures compliance with pump flow rate and temperature limits. These input driving modules benefit from detailed online simulations that are assimilated to measurement data with Bayesian filtering. The digital twin is demonstrated in three case studies: a one-year long-term operational period showcasing maintenance planning capabilities, short-term accuracy refinement with high-frequency measurements, and system shock capturing that demonstrates real-time recalibration capabilities when change in boundary conditions. These demonstrations validate robustness for health-aware and constraint-informed nuclear plant operation, with general applicability to other advanced reactor concepts and complex engineering systems. • Data-driven Digital twin framework of a Fluoride-salt-cooled High-temperature Reactor. • Reinforcement learning supervisory agent for driving physical asset setpoints. • Apply Bayesian filtering for virtual model adaptation with state-parameter estimation. • Demonstrations for long-term operations, accuracy refinements, and a system shock.

A process optimization framework for laser direct energy deposition: Densification, microstructure, and mechanical properties of an Fe[sbnd]Cr alloy

Development of electrification across industries impose higher demand on power converter reliability. To enhance reliability, this paper proposes a novel digital twin (DT) framework using convolutional neural network (CNN) for converter real-time condition monitoring. The DT consists of a physics-based model, an observer and a CNN-ResNet based parameter estimation method. The parameter estimation method provides accurate parameter estimation for the physic-based model using real-time electrical measurements and estimation values from the observer. Therefore, the proposed DT can achieve fast and accurate online parameter identification under different load conditions without extra hardware setup. Moreover, the DT can mirror real-time output waveforms of its physical counterpart. Simulations and experiments are conducted to validate the effectiveness of the proposed DT framework.

With the prompt digital revolution in architecture, engineering, and construction (AEC), it is crucial to set the early practical steps for advanced digital technology namely digital twin technology. Although theoretical evidence on the potential of digital twins exists in AEC scope, the practical framework to the construction and operation of user-centred digital twin is yet to be investigated. Hence, this applied research investigates systematic methods and techniques for the construction and enablement of a user-centred digital twin paving the way to advanced digital applications in AEC centred on the user of the built environment. As a result, the framework unleashes a systematic roadmap to the creation and development of a city-scale digital twin centred on the human and capable of describing, analyzing, and assessing a built context per its users and usability manner. Further, the framework pours the foundations for a spectrum of digital twin applications in the scope of architectural design, building construction, infrastructure engineering, and facility management. The production of this research is foreseen to outline a systematic and transferable framework for the construction and enablement of a user-centred digital twin.

Digital Twin is an emerging technology at the forefront of Industry 4.0, with the ultimate goal of combining the physical space and the virtual space. To date, the Digital Twin concept has been applied in many engineering fields, providing useful insights in the areas of engineering design, manufacturing, automation, and construction industry. While the nexus of various technologies opens up new opportunities with Digital Twin, the technology requires a framework to integrate the different technologies, such as the Building Information Model used in the Building and Construction industry. In this work, an Information Fusion framework is proposed to seamlessly fuse heterogeneous components in a Digital Twin framework from the variety of technologies involved. This study aims to augment Digital Twin in buildings with the use of AI and 3D reconstruction empowered by unmanned aviation vehicles. We proposed a drone-based Digital Twin augmentation framework with reusable and customisable components. A proof of concept is also developed, and extensive evaluation is conducted for 3D reconstruction and applications of AI for defect detection.KeywordsDigital Twin3D reconstructionArtificial Intelligence (AI)Information augmentationUnmanned aerial vehicle (UAV)

PurposeThis study aims to investigate the effect of mechanical peening on the cooling rate of a subsequently deposited layer in a hybrid additive manufacturing (AM) process.Design/methodology/approachIn this experimental study, 20 layers of 316 L stainless steel are built via directed energy deposition, with the tenth layer being subject to various peening processes (shot peening, hammer peening and laser shock peening). The microstructure of the eleventh layer of all the samples is then characterized to estimate the cooling rate.FindingsThe measurements indicate that the application of interlayer peening causes a reduction in primary cellular arm spacing and an increase in micro segregation as compared to a sample prepared without interlayer peening. Both factors indicate an increase in the cooling rate brought about by the interlayer peening.Practical implicationsThis work provides insight into process design for hybrid AM processes as cooling rates are known to influence mechanical properties in laser-based AM.Originality/valueTo the best of the authors’ knowledge, this work is the first of its kind to evaluate the effects of interlayer peening on a subsequently deposited layer in a hybrid AM process.

A digital twin (DT) framework for Internet‐of‐thing (IoT) networks is proposed where unmanned aerial vehicles (UAVs) acting as flying mobile edge computing (MEC) servers support the task offloading on the fly. The considered DT model is very well suitable for industrial automation with the strict constraints of mission‐critical services' ultra‐reliable low‐latency communication (URLLC) links. To support low‐latency IoT devices, we formulate the end‐to‐end (e2e) latency minimisation problem of digital twin‐aided offloading UAV‐URLLC. Specifically, the minimised latency is obtained by jointly optimising both communication and computation parameters, namely power, offloading factors, and the processing rate of IoT devices and MEC‐UAV servers. Due to the highly non‐convex optimisation problem, we first consider the K‐means clustering algorithm to optimally deploy the on‐demand UAVs. Then, an alternative optimisation approach combined with appropriate inner approximations is effectively exploited to tackle this challenge. We demonstrate the effectiveness of the proposed DT framework through representative numerical results.

Digital twin-driven architecture for AIoT-based energy service provision and optimal energy trading between smart nanogrids

Digital Twin technology is rapidly emerging as a transformative force in various industries, playing a pivotal role in the advancement of Industry 4.0. As industries evolve, the implementation of Digital Twin is anticipated to drive significant technological progress across sectors such as manufacturing, smart cities, healthcare, and transportation. This paper presents a layered Digital Twin framework that synthesizes recent advances in sensing, data analytics, and machine learning to enable real-time monitoring, analysis, and predictive capabilities for modern power systems. By leveraging these advanced sensors, the Digital Twin framework enables more accurate system modeling, enhanced situational awareness, and improved decision-making processes. This approach aims to significantly transform traditional smart grid operations by offering a more responsive, resilient, and efficient energy management system, ultimately contributing to the optimization and modernization of existing power infrastructure. Furthermore, by highlighting key smart grid applications, the paper demonstrates the effectiveness of Digital Twin and sensor technology in optimizing power distribution, reducing downtime, and addressing prevalent energy challenges, thereby paving the way for resilient and intelligent power systems.